在实现结构分析法识别手写汉字时，笔划抽取是关键所在。
In developing handprinted Chinese characters recognition system by the structural approach. the stroke extraction is all important problem.
本文提出对手写相似汉字进行识别的支持向量机方法。
This paper presents a recognition method of similar Chinese handwriting by support vector machine.
针对手写体汉字识别过程中的特征抽取，提出了一种改进的抽取笔画平面的方法。
According to the feature extraction of the handwritten Chinese character recognition, an improved extracting stroke plane method was proposed.
从而进一步提高了脱机手写汉字识别的正确率。
Hence, improve the correct rate of off-line handwritten Chinese character recognition.
在手写汉字的自动识别方面，至今普遍采用构造解析和匹配相结合的方法。
The method of combining structure analysis and match is generally used for recognition of handwritten Chinese characters.
手写汉字识别实验样本量巨大，使得实验无法在有限时间内在单机上运行完成。
The amount of samples in Handwritten Chinese Characters Recognition is so huge, so that experiments are impossible to be completed within limited time on only one computer.
本文提出一种对限制性手写汉字的结构识别方法。
A structural recognition method for constrained handprinted Chinese characters is proposed in this paper.
本文提出一种手写印刷体汉字识别方法，使用该方法无需先对汉字进行细化和平滑处理。
A proper method for the recognition of handprinted Chinese characters is presented here, without thinning the character image and smoothing it before hand.
现在有很多汉字和英文的联机手写识别产品问世。
Now there are many products of online handwriting recognition of Chinese characters and English characters.
许多实际的模式识别问题如对手写体汉字的识别，都属于大规模的模式识别问题。
Many practical pattern recognition problems, such as recognition of handwritten Chinese characters belong to the pattern recognition problems of large scale.
本文主要研究聚类分析在手写汉字识别中的应用。
This thesis mainly studies the application of the clustering analysis in handwritten Chinese character recognition.
不同soa条件下较高的检测率证实了手写汉字的可识别性，这为笔迹鉴定搭建了理论基石。
High correct response rate under different SOA level testify the handwriting can be recognized that is base theory of handwriting identification.
通过对神经网络集成的理论分析，提出了一种多级神经网络结构的手写体汉字识别模型。
By analyzing the theory of neural network integration, I developed a multi-level neural network model for recognition handwritten Chinese characters.
提出一个基于多重曲率计算的角点检测算法，对联机手写汉字识别中的笔划拐点进行提取。
An algorithm for stroke corner detection based on curvature multi-calculation is proposed to extract characteristics for OLCCR (on-line handwritten Chinese character recognition).
本文介绍用于识别手写印刷体汉字的二维扩展属性文法方法中文法归约阶段的工作。
The work on grammar reductions in Two-Dimensional Extended Attribute Grammars is presented for the recognition of hand-printed Chinese characters.
在手写汉字识别的研究中，鲜有研究者提出建立手写汉字的数学模型，本文在这方面作了一些探讨。
In the research of handwriting Chinese character recognition, no researcher raised a mathematical model of handwriting Chinese characters which is discussed in this paper.
手写体汉字的识别试验验证了所给方法的有效性。
The experiments of handwritten Chinese character recognition show the effectiveness of the proposed approach.
构建一种基于反馈结构的手写体汉字识别系统。
A system of handwritten Chinese characters recognition based on feedback structure is constructed.
手写体汉字书写变形是手写体汉字识别预处理阶段的重要问题之一。
Stroke deformation is an important factor to effect the performance of the handwritten Chinese character recognition system.
这些融合策略经联机手写体汉字识别系统测试，系统性能有了较大提高。
These strategies are experimentally tested on online handwritten Chinese character recognition system and their effectiveness is considered.
以笔划为基元结合笔划的顺序来表示汉字的结构信息，在此基础上提出了一种手写汉字识别的匹配算法。
This paper takes stroke segment as pattern primitive to represent the structure information of Chinese character. On the basis, a new algorithm to recognize handwritten Chinese character is proposed.
研究了基于自适应特征融合及模块神经网络的手写体汉字识别。
I studied the handwritten Chinese character recognition techniques based on adaptive information fusion and module neural networks.
采用该特征对有限集手写体汉字进行识别，初步实验结果表明该方法十分有效。
The result of experiment shows high recognition rate which indicates that the method is very effective.
研究了手写体汉字识别技术，采用改进BP算法进行网络训练，提高了算法的收敛速度。
A technological research on recognition of handwritten Chinese characters based on improved BP algorithm is summarized. This algorithm can enhance convergence speed.
提出的脱机手写体汉字识别系统主要研究特征提取和分类识别两个模块。
The proposed off-line handwritten Chinese character recognition system was composed of a feature extraction module and a recognition module.
文章提出了一种基于多重隐马尔可夫模型和区域投影变换的手写体汉字识别新方法。
A new approach for handwritten Chinese character recognition based on multiple hidden Markov model classifiers and sub-region projection transform is proposed in the thesis.
建模的目的通常有两个：一是手写汉字的表示或描述，二是手写汉字的识别。
Generally, there are two purposes to raise a model: First one is for description, second one is for recognition.
手写数字识别和脱机手写汉字识别的实际应用验证了所提的理论和方法。
Practice in handwritten numeral recognition and off line handwritten Chinese character recognition strongly supports the ideas and the methods.
非限定手写汉字分割问题是手写汉字识别的关键问题，也是目前的分割-识别框架中的难点。
The segmentation of unconstrained handwritten Chinese words is the key problem of handwritten Chinese words recognition. It is also the difficulty of current segmentation-recognition truss.
应用字符的特征矩阵设计了一个手写体汉字的分类识别算法，取得了较好的效果。
A handwritten Chinese character classifying algorithm is designed based on the character feature matrix with the excellent classifying effect.
应用推荐